raid_roberta

README.md

@@ -1,6 +1,6 @@
 ---
 license: mit
-base_model: FacebookAI/roberta-base
+base_model: FacebookAI/roberta-large
 tags:
 - generated_from_trainer
 metrics:
@@ -15,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # results
 
-This model is a fine-tuned version of [FacebookAI/roberta-base](https://huggingface.co/FacebookAI/roberta-base) on the None dataset.
+This model is a fine-tuned version of [FacebookAI/roberta-large](https://huggingface.co/FacebookAI/roberta-large) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0000
-- Accuracy: 1.0
+- Loss: 0.6933
+- Accuracy: 0.5
 
 ## Model description
 
@@ -49,9 +49,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.0           | 1.0   | 401  | 0.0000          | 1.0      |
-| 0.0           | 2.0   | 802  | 0.0000          | 1.0      |
-| 0.0           | 3.0   | 1203 | 0.0000          | 1.0      |
+| 0.7061        | 1.0   | 1590 | 0.6938          | 0.5      |
+| 0.7008        | 2.0   | 3180 | 0.6935          | 0.5      |
+| 0.6962        | 3.0   | 4770 | 0.6933          | 0.5      |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "FacebookAI/roberta-base",
+  "_name_or_path": "FacebookAI/roberta-large",
   "architectures": [
     "RobertaForSequenceClassification"
   ],
@@ -9,14 +9,14 @@
   "eos_token_id": 2,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "hidden_size": 1024,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 4096,
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 514,
   "model_type": "roberta",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ce87e3b9f38cd7c7fd201d33773e6e8432079fd626984ee84d3ec5bfdb028fc
-size 498612824
+oid sha256:49e6d2f88c1c23b49822246e87fa67730e730110e5017d854f1cc4bae49fb776
+size 1421495416

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd6394ea81340371cea7706e216bd75649b086342125e3aff06582c79a40f62d
+oid sha256:1add2f0f43915579b20ac5e06b963598427a55e8d1a4b9a73bdd543ffab92330
 size 4664